Manage jobs
Submitting and managing jobs in the Cirrus HPC and HTC clusters
Start here
Cluster specific information INCD provides acess to several HPC computing clusters. The policies...
Queues information
List of Queues INCD-Lisbon cluster (cirrus.a.incd.pt) Name Jobs max elapsed time access Me...
Manage slurm jobs
How to handle jobs management using slurm batch system. Used at Minho and ISEC and Lisbon data c...
Slurm
Slurm's architecture Slurm is made of a slurmd daemon running on each compute node and a central...
Jobs information
List all current jobs for a user: squeue -u <username> List all running jobs for a user: ...
My first slurm job
Examples Submit a simple MPI job On this example we run a small MPI application doing the fo...
overview of the resources offered
sinfo : overview of the resources offered by the cluster By default, sinfo lists the available ...
show job accounting data
sacct: displays accounting data for all jobs and job steps in the Slurm job accounting log or Slu...
stop or cancel jobs
scancel : used to signal jobs or job steps that are under the control of Slurm The command scan...
Show jobs information in queue
squeue: view information about jobs located in the Slurm scheduling queue. gqueue: squeue alias ...
How to run parallel job's with srun
srun : Used to submit/initiate job or job step Typically, srun is invoked from a SLURM job scr...
Preparing the Environment
There are lots of litte tweaks we need in order to prepate the environment for running specific s...
Interactive Sessions
Slurm allow interactive sessions into the workernodes, using ssh, but within a valid job allocati...
Job pipeline using slurm dependencies
Some times we need to launch a list of jobs that execute in sequence, one after another. In thos...
Use of user QOS for CPU jobs
In order to use QOS you will to have an assigned user QOS. In the following example the user will...
GPU user guide
How to Run a Job with a GPU
Let's run the gravitational N-body simulation found on the CUDA toolkit samples on a GPU. This ex...
Use QOS to run GPU jobs
This page it's dedicate to users who want to run GPU's and have a QOS. GPU JOB submission usin...
Deep Learning Example
The INCD-Lisbon facility provide a few GPU, check the Comput Node Specs page. Login on the submi...
How to selected a GPU
Select any GPU On this example we choose one GPU with at least 8192 MB memory. #!/bin/bash ...
Troubleshooting information
UDocker Containers
Availability of udocker containers directly on CVMFS read-only filesystem in order to speedup the...
Monitoring
Useful commands to monitor jobs or consumption
Quality of Service (QOS)
Quality of Service (QoS) is used to limite the characteristics that a job can have. Default QOS ...